© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20021
    Prev
    Next
    INDEX
    Explanations

    `CCCC`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    зÑĮ
    -0.06
     ado
    -0.05
    nh
    -0.05
     ov
    -0.05
    åıĺåĬ¨
    -0.05
    adam
    -0.05
    å¤Ń
    -0.05
    ucs
    -0.05
    aye
    -0.05
    xce
    -0.05
    POSITIVE LOGITS
     teng
    0.07
    ollo
    0.06
    ãĥĩãĤ£ãĥ³ãĤ°
    0.06
     hyvin
    0.06
    Ñľ
    0.05
    æīī
    0.05
     sót
    0.05
    ambil
    0.05
    umba
    0.05
    ukung
    0.05
    Activations Density 0.002%

    No Known Activations